Back to results
US 2020/0089735 A1Published application
System and Method for Using Data and Angles to Automatically Generate a Narrative Story
AssigneeNarrative Science Inc.
InventorsLawrence A. Birnbaum, Kristian J. Hammond, Nicholas D. Allen, John R. Templon
Life of this patent
Estimating the term…
Abstract
A system and method for automatically generating a narrative story receives data and information pertaining to a domain event. The received data and information and/or one or more derived features are then used to identify a plurality of angles for the narrative story. The plurality of angles is then filtered, for example through use of parameters that specify a focus for the narrative story, length of the narrative story, etc. Points associated with the filtered plurality of angles are then assembled and the narrative story is rendered using the filtered plurality of angles and the assembled points.
Claims22
An apparatus for automatically generating a narrative story about a structured data set, the narrative story comprising natural language text arranged in a narrative format, the apparatus comprising:
- a memory in which a plurality of data structures are stored, each of a plurality of the data structures being representative of a characterization of data and having an associated applicability condition, the associated applicability condition for testing against data within or derived from the structured data set to support a determination as to whether the representative characterization for the applicability condition's associated data structure is an accurate characterization of the structured data set;
- and
- a processor in cooperation with the memory, the processor configured to:
- compute a plurality of derived features from the structured data set, wherein the structured data set comprises data that falls into a plurality of fields and/or categories and which relates to specific events, situations, entities, or aggregations thereof, and wherein the data of the structured data set includes numeric values;
- test data against a plurality of the applicability conditions for a plurality of the data structures in the memory, wherein the tested data comprises at least one of (1) data within the structured data set and (2) data within the computed derived features;
- in response to the tests, (1) determine that a plurality of the data structures are candidate data structures that accurately characterize the structured data set, and (2) filter the candidate data structures to select at least one of the candidate data structures;
- and
- automatically render the narrative story natural language text for display based at least in part on (1) the selected at least one candidate data structure and (2) at least one of (i) data within the structured data set and (ii) data within the computed derived features such that the rendered narrative story natural language text describes the structured data set in accordance with the at least one characterization represented by the selected at least one candidate data structure.
5 more elements
A computer program product for automatically generating a narrative story about a structured data set, the narrative story comprising natural language text arranged in a narrative format, the computer program product comprising:
- a plurality of computer executable instructions resident on a non-transitory computer-readable storage medium, the instructions, when executed by a computing device, configured to cause the computing device to:
- access a plurality of data structures in a memory, each of a plurality of the data structures being representative of a characterization of data and having an associated applicability condition, the associated applicability condition for testing against data within or derived from the structured data set to support a determination as to whether the representative characterization for the applicability condition's associated data structure is an accurate characterization of the structured data set;
- compute a plurality of derived features from the structured data set, wherein the structured data set comprises data that falls into a plurality of fields and/or categories and which relates to specific events, situations, entities, or aggregations thereof, and wherein the data of the structured data set includes numeric values;
- test data against a plurality of the applicability conditions for a plurality of the accessed data structures, wherein the tested data comprises at least one of (1) data within the structured data set and (2) data within the computed derived features;
- in response to the tests, (1) determine that a plurality of the data structures are candidate data structures that accurately characterize the structured data set, and (2) filter the candidate data structures to select at least one of the candidate data structures;
- and
- automatically render the narrative story natural language text for display based at least in part on (1) the selected at least one candidate data structure and (2) at least one of (i) data within the structured data set and (ii) data within the computed derived features such that the rendered narrative story natural language text describes the structured data set in accordance with the at least one characterization represented by the selected at least one candidate data structure.
4 more elements
A method for automatically generating a narrative story about a structured data set, the narrative story comprising natural language text arranged in a narrative format, the method comprising:
- a processor computing a plurality of derived features from the structured data set, wherein the structured data set comprises data that falls into a plurality of fields and/or categories and which relates to specific events, situations, entities, or aggregations thereof, and wherein the data of the structured data set includes numeric values;
- a processor accessing a plurality of data structures in a memory, each of a plurality of the data structures being representative of a characterization of data and having an associated applicability condition, the associated applicability condition for testing against at least one of (1) data within the structured data set and (2) data within the computed derived features to support a determination as to whether the representative characterization for the applicability condition's associated data structure is an accurate characterization of the structured data set;
- a processor testing data against a plurality of the applicability conditions for a plurality of the accessed data structures, wherein the tested data comprises at least one of (1) data within the structured data set and (2) data within the computed derived features;
- in response to the testing, a processor, (1) determining that a plurality of the data structures are candidate data structures that accurately characterize the structured data set, and (2) filtering the candidate data structures to select at least one of the candidate data structures;
- and
- a processor automatically rendering the narrative story text for display based at least in part on (1) the selected at least one candidate data structure and (2) at least one of (i) data within the structured data set and (ii) data within the computed derived features such that the rendered narrative story natural language text describes the structured data set in accordance with the at least one characterization represented by the selected at least one candidate data structure.
3 more elements
Dependencies are inferred from the claim text.